English
Related papers

Related papers: An Efficient and Margin-Approaching Zero-Confidenc…

200 papers

Current adversarial attacks for multi-class classifiers choose the target class for a given input naively, based on the classifier's confidence levels for various target classes. We present a novel adversarial targeting method, \textit{MALT…

Machine Learning · Computer Science 2024-07-03 Odelia Melamed , Gilad Yehudai , Adi Shamir

White box adversarial perturbations are generated via iterative optimization algorithms most often by minimizing an adversarial loss on a $\ell_p$ neighborhood of the original image, the so-called distortion set. Constraining the…

Machine Learning · Computer Science 2021-02-16 Ehsan Kazemi , Thomas Kerdreux , Liquang Wang

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…

Machine Learning · Computer Science 2019-10-23 Saeid Samizade , Zheng-Hua Tan , Chao Shen , Xiaohong Guan

With the fast development of machine learning technologies, deep learning models have been deployed in almost every aspect of everyday life. However, the privacy and security of these models are threatened by adversarial attacks. Among…

Cryptography and Security · Computer Science 2022-01-14 Rui Wang

Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Pascal Zimmer , Sébastien Andreina , Giorgia Azzurra Marson , Ghassan Karame

Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial…

Machine Learning · Computer Science 2024-06-13 Feiyang Wang , Xingquan Zuo , Hai Huang , Gang Chen

As deep learning models are increasingly deployed in safety-critical applications, evaluating their vulnerabilities to adversarial perturbations is essential for ensuring their reliability and trustworthiness. Over the past decade, a large…

Machine Learning · Computer Science 2025-03-12 Yong Xie , Weijie Zheng , Hanxun Huang , Guangnan Ye , Xingjun Ma

Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

We propose a scheme for defending against adversarial attacks by suppressing the largest eigenvalue of the Fisher information matrix (FIM). Our starting point is one explanation on the rationale of adversarial examples. Based on the idea of…

Machine Learning · Computer Science 2019-09-16 Chaomin Shen , Yaxin Peng , Guixu Zhang , Jinsong Fan

Time-series forecasting aims to predict future values by modeling temporal dependencies in historical observations. It is a critical component of many real-world systems, where accurate forecasts improve operational efficiency and help…

Machine Learning · Computer Science 2026-04-15 Gamze Kirman Tokgoz , Onat Gungor , Tajana Rosing , Baris Aksanli

Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure. Conversely,…

Machine Learning · Computer Science 2025-05-07 Thomas Winninger , Boussad Addad , Katarzyna Kapusta

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Dong Lao , Yuxiang Zhang , Haniyeh Ehsani Oskouie , Yangchao Wu , Alex Wong , Stefano Soatto

Research in adversarial learning has primarily focused on homogeneous unstructured datasets, which often map into the problem space naturally. Inverting a feature space attack on heterogeneous datasets into the problem space is much more…

A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…

Machine Learning · Computer Science 2024-04-09 Anshuman Suri , Yifu Lu , Yanjin Chen , David Evans

Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that look like the training data, but slightly perturbed, in a way…

Machine Learning · Computer Science 2021-01-19 Mahmoud Hossam , Trung Le , He Zhao , Dinh Phung

Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation. Adversarial examples, which are carefully crafted with a malicious purpose, can lead to erroneous predictions, resulting in catastrophic…

Machine Learning · Computer Science 2021-11-19 Mingu Kang , Trung Quang Tran , Seungju Cho , Daeyoung Kim

Deep neural networks are susceptible to small-but-specific adversarial perturbations capable of deceiving the network. This vulnerability can lead to potentially harmful consequences in security-critical applications. To address this…

Computer Vision and Pattern Recognition · Computer Science 2018-06-29 Jasjeet Dhaliwal , Saurabh Shintre

Deep neural networks are susceptible to adversarial inputs and various methods have been proposed to defend these models against adversarial attacks under different perturbation models. The robustness of models to adversarial attacks has…

Machine Learning · Computer Science 2022-11-01 Jian Vora , Pranay Reddy Samala

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output label~(hard label) to a queried data input. We propose a…

Machine Learning · Computer Science 2021-06-14 Satya Narayan Shukla , Anit Kumar Sahu , Devin Willmott , J. Zico Kolter

Although adversarial robustness has been extensively studied in white-box settings, recent advances in black-box attacks (including transfer- and query-based approaches) are primarily benchmarked against weak defenses, leaving a significant…

Machine Learning · Computer Science 2026-02-18 Mohamed Djilani , Salah Ghamizi , Maxime Cordy